FIELD: computer technology.
SUBSTANCE: invention relates to the field of computer technology, in particular to a method for building of synthetic images of computer tomography (hereinafter – CT) based on image data of magnetic-resonance imaging (hereinafter – MRI). A method for building synthetic CT images based on MRI image data is proposed, containing: a preparatory stage, at which a dataset consisting of a text sample of CT image and MRI image data is preliminary processed, which consists in removal of parts on CT images, which cannot be synthesized from MRI; a generative-adversarial network with two discriminators is trained for obtaining synthetic CT images, the first discriminator receives at an input preliminary processed images from the dataset, and the second one – CT image synograms; the resulting CT image is registered on the initial MRI image, using hard conversion, using mutual information as target metrics of combination quality; a working stage, at which T1-weighted MRI image enters a computing device; a format of the received image is validated; CT images are generated based on MRI images by means of cyclic generative-adversarial networks; the result is output by means of an output module.
EFFECT: invention provides for an increase in the quality of building of synthetic CT images based on MRI image data.
5 cl, 2 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD FOR DETERMINING DEFECTS IN THE IMAGE OF COMPOSITE PRODUCTS | 2022 |
|
RU2807288C1 |
SYSTEM FOR RECOVERY OF ROCK SAMPLE THREE-DIMENSIONAL STRUCTURE | 2018 |
|
RU2718409C1 |
SEGMENTATION OF HUMAN TISSUES IN COMPUTER IMAGE | 2017 |
|
RU2654199C1 |
NEURAL NETWORK FOR GENERATING SYNTHETIC MEDICAL IMAGES | 2017 |
|
RU2698997C1 |
DEVICE FOR CREATION OF MULTIDIMENSIONAL VIRTUAL IMAGES OF HUMAN RESPIRATORY ORGANS AND METHOD FOR CREATION OF VOLUMETRIC IMAGES, USING DEVICE | 2021 |
|
RU2783364C1 |
SYSTEMS AND METHODS OF TRAINING GENERATIVE-ADVERSARIAL NETWORKS, AS WELL AS USE OF TRAINED GENERATIVE-ADVERSARIAL NETWORKS | 2019 |
|
RU2819619C2 |
METHOD OF CREATING FULL-LENGTH ANIMATED AVATAR OF PERSON FROM ONE IMAGE OF PERSON, COMPUTING DEVICE AND MACHINE-READABLE MEDIUM FOR IMPLEMENTATION THEREOF | 2023 |
|
RU2813485C1 |
ANNOTATION IDENTIFICATION TO IMAGE DESCRIPTION | 2015 |
|
RU2699416C2 |
METHOD FOR GENERATING THREE-DIMENSIONAL POINT CLOUDS | 2020 |
|
RU2745445C1 |
METHOD OF BRAIN SEGMENT LOCALIZATION | 2020 |
|
RU2743608C1 |
Authors
Dates
2022-08-15—Published
2020-05-15—Filed